Operator Reference

HALCON Operator Reference / Deep Learning / Framework

• HDevelop
• .NET
• Python
• C++
• C

ClassesClasses | | Operators

create_dl_layer_loss_distanceT_create_dl_layer_loss_distanceCreateDlLayerLossDistanceCreateDlLayerLossDistancecreate_dl_layer_loss_distance (Operator)

create_dl_layer_loss_distanceT_create_dl_layer_loss_distanceCreateDlLayerLossDistanceCreateDlLayerLossDistancecreate_dl_layer_loss_distance — Create a distance loss layer.

Signature

create_dl_layer_loss_distance( : : DLLayerInput, DLLayerTarget, DLLayerWeights, LayerName, DistanceType, LossWeight, GenParamName, GenParamValue : DLLayerLossDistance)

Herror T_create_dl_layer_loss_distance(const Htuple DLLayerInput, const Htuple DLLayerTarget, const Htuple DLLayerWeights, const Htuple LayerName, const Htuple DistanceType, const Htuple LossWeight, const Htuple GenParamName, const Htuple GenParamValue, Htuple* DLLayerLossDistance)

void CreateDlLayerLossDistance(const HTuple& DLLayerInput, const HTuple& DLLayerTarget, const HTuple& DLLayerWeights, const HTuple& LayerName, const HTuple& DistanceType, const HTuple& LossWeight, const HTuple& GenParamName, const HTuple& GenParamValue, HTuple* DLLayerLossDistance)

HDlLayer HDlLayer::CreateDlLayerLossDistance(const HDlLayer& DLLayerTarget, const HDlLayer& DLLayerWeights, const HString& LayerName, const HString& DistanceType, double LossWeight, const HTuple& GenParamName, const HTuple& GenParamValue) const

HDlLayer HDlLayer::CreateDlLayerLossDistance(const HDlLayer& DLLayerTarget, const HDlLayer& DLLayerWeights, const HString& LayerName, const HString& DistanceType, double LossWeight, const HString& GenParamName, const HString& GenParamValue) const

HDlLayer HDlLayer::CreateDlLayerLossDistance(const HDlLayer& DLLayerTarget, const HDlLayer& DLLayerWeights, const char* LayerName, const char* DistanceType, double LossWeight, const char* GenParamName, const char* GenParamValue) const

HDlLayer HDlLayer::CreateDlLayerLossDistance(const HDlLayer& DLLayerTarget, const HDlLayer& DLLayerWeights, const wchar_t* LayerName, const wchar_t* DistanceType, double LossWeight, const wchar_t* GenParamName, const wchar_t* GenParamValue) const   ( Windows only)

static void HOperatorSet.CreateDlLayerLossDistance(HTuple DLLayerInput, HTuple DLLayerTarget, HTuple DLLayerWeights, HTuple layerName, HTuple distanceType, HTuple lossWeight, HTuple genParamName, HTuple genParamValue, out HTuple DLLayerLossDistance)

HDlLayer HDlLayer.CreateDlLayerLossDistance(HDlLayer DLLayerTarget, HDlLayer DLLayerWeights, string layerName, string distanceType, double lossWeight, HTuple genParamName, HTuple genParamValue)

HDlLayer HDlLayer.CreateDlLayerLossDistance(HDlLayer DLLayerTarget, HDlLayer DLLayerWeights, string layerName, string distanceType, double lossWeight, string genParamName, string genParamValue)

def create_dl_layer_loss_distance(dllayer_input: HHandle, dllayer_target: HHandle, dllayer_weights: HHandle, layer_name: str, distance_type: str, loss_weight: float, gen_param_name: MaybeSequence[str], gen_param_value: MaybeSequence[str]) -> HHandle

Description

The operator create_dl_layer_loss_distancecreate_dl_layer_loss_distanceCreateDlLayerLossDistanceCreateDlLayerLossDistancecreate_dl_layer_loss_distance creates a distance loss layer whose handle is returned in DLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistancedllayer_loss_distance.

This layer expects multiple layers as input:

• DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input: Specifies the prediction (e.g., a softmax layer).

• DLLayerTargetDLLayerTargetDLLayerTargetDLLayerTargetdllayer_target: Specifies the target sequences (originating from the ground truth information).

• DLLayerWeightsDLLayerWeightsDLLayerWeightsDLLayerWeightsdllayer_weights: Specifies the weight sequences. This parameter is optional. If an empty tuple [] is passed for all values the weighting factor 1.0 is used.

The parameter LayerNameLayerNameLayerNamelayerNamelayer_name sets an individual layer name. Note that if creating a model using create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelcreate_dl_model each layer of the created network must have a unique name.

The parameter LossWeightLossWeightLossWeightlossWeightloss_weight is an overall loss weight if there are multiple losses in the network.

The parameter DistanceTypeDistanceTypeDistanceTypedistanceTypedistance_type determines which distance measure is applied. Currently, 'l2'"l2""l2""l2""l2" and 'l1'"l1""l1""l1""l1" are implemented. Depending on the generic parameter 'reduce'"reduce""reduce""reduce""reduce" this results in

• L2 loss distance as a tensor: in this case loss is the tensor of the same size as DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input.

• L2 loss distance as a scalar: where is a number of elements in DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input.

• L1 loss distance as a tensor: in this case loss is the tensor of the same size as DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input.

• L1 loss distance as a scalar: where is a number of elements in DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input.

Thus DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input, DLLayerTargetDLLayerTargetDLLayerTargetDLLayerTargetdllayer_target and DLLayerWeightsDLLayerWeightsDLLayerWeightsDLLayerWeightsdllayer_weights should have the same size. Setting the weights in DLLayerWeightsDLLayerWeightsDLLayerWeightsDLLayerWeightsdllayer_weights to 1 will result in a loss normalized over the number of elements.

The following generic parameters GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name and the corresponding values GenParamValueGenParamValueGenParamValuegenParamValuegen_param_value are supported:

'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output":

Determines whether apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model will include the output of this layer in the dictionary DLResultBatchDLResultBatchDLResultBatchDLResultBatchdlresult_batch even without specifying this layer in OutputsOutputsOutputsoutputsoutputs ('true'"true""true""true""true") or not ('false'"false""false""false""false").

Default: 'false'"false""false""false""false"

'reduce'"reduce""reduce""reduce""reduce":

Determines whether the output of the layer is reduced:

• 'true'"true""true""true""true": The output is reduced to a scalar.

• 'false'"false""false""false""false": The output of the layer is a tensor, where each element is a 'per-pixel' loss (squared differences).

Default: 'true'"true""true""true""true".

Certain parameters of layers created using this operator create_dl_layer_loss_distancecreate_dl_layer_loss_distanceCreateDlLayerLossDistanceCreateDlLayerLossDistancecreate_dl_layer_loss_distance can be set and retrieved using further operators. The following tables give an overview, which parameters can be set using set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and which ones can be retrieved using get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param or get_dl_layer_paramget_dl_layer_paramGetDlLayerParamGetDlLayerParamget_dl_layer_param. Note, the operators set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param and get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param require a model created by create_dl_modelcreate_dl_modelCreateDlModelCreateDlModelcreate_dl_model.

Layer Parameters	set	get
'input_layer'"input_layer""input_layer""input_layer""input_layer" (DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input, DLLayerTargetDLLayerTargetDLLayerTargetDLLayerTargetdllayer_target, and/or DLLayerWeightsDLLayerWeightsDLLayerWeightsDLLayerWeightsdllayer_weights)		x
'loss_weight'"loss_weight""loss_weight""loss_weight""loss_weight" (LossWeightLossWeightLossWeightlossWeightloss_weight)	x	x
'name'"name""name""name""name" (LayerNameLayerNameLayerNamelayerNamelayer_name)	x	x
'output_layer'"output_layer""output_layer""output_layer""output_layer" (DLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistancedllayer_loss_distance)		x
'shape'"shape""shape""shape""shape"		x
'type'"type""type""type""type"		x
'distance_type'"distance_type""distance_type""distance_type""distance_type" (DistanceTypeDistanceTypeDistanceTypedistanceTypedistance_type)		x

Generic Layer Parameters	set	get
'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output"	x	x
'num_trainable_params'"num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params"		x
'reduce'"reduce""reduce""reduce""reduce"	x	x

Execution Information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

Parameters

DLLayerInputDLLayerInputDLLayerInputDLLayerInputdllayer_input (input_control)  dl_layer → HDlLayer, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Input layer.

DLLayerTargetDLLayerTargetDLLayerTargetDLLayerTargetdllayer_target (input_control)  dl_layer → HDlLayer, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Target layer.

DLLayerWeightsDLLayerWeightsDLLayerWeightsDLLayerWeightsdllayer_weights (input_control)  dl_layer → HDlLayer, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Weights layer.

LayerNameLayerNameLayerNamelayerNamelayer_name (input_control)  string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Name of the output layer.

DistanceTypeDistanceTypeDistanceTypedistanceTypedistance_type (input_control)  string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Type of distance.

Default: 'l2' "l2" "l2" "l2" "l2"

List of values: 'l1'"l1""l1""l1""l1", 'l2'"l2""l2""l2""l2"

LossWeightLossWeightLossWeightlossWeightloss_weight (input_control)  number → HTuplefloatHTupleHtuple (real) (double) (double) (double)

Loss weight. Applies to all losses, if several losses occur in the network.

Default: 1.0

GenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (input_control)  attribute.name(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)

Generic input parameter names.

Default: []

List of values: 'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output", 'reduce'"reduce""reduce""reduce""reduce"

GenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (input_control)  attribute.value(-array) → HTupleMaybeSequence[str]HTupleHtuple (string) (string) (HString) (char*)

Generic input parameter values.

Default: []

Suggested values: 'true'"true""true""true""true", 'false'"false""false""false""false"

DLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistanceDLLayerLossDistancedllayer_loss_distance (output_control)  dl_layer → HDlLayer, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Distance loss layer.

Module

Deep Learning Professional

---

ClassesClasses | | Operators